# Adaptive Graphical Model Network for 2D Handpose Estimation

arXiv: https://arxiv.org/abs/1909.08205 · HTML: https://mlsanity.com/paper/1909.08205/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.09554/) (2021)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [Identity-Aware Hand Mesh Estimation and Personalization from RGB Images](https://mlsanity.com/paper/2209.10840/) (2022)
- [MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2110.15327/) (2021)
- [Fast Monocular Hand Pose Estimation on Embedded Systems](https://mlsanity.com/paper/2102.07067/) (2021)
- [Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation](https://mlsanity.com/paper/2105.10904/) (2021)
- [Deep Dependency Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.00633/) (2023)
- [Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation](https://mlsanity.com/paper/2304.05548/) (2023)
- [Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification](https://mlsanity.com/paper/2404.11667/) (2024)

## Abstract (arXiv)

In this paper, we propose a new architecture called Adaptive Graphical Model Network (AGMN) to tackle the task of 2D hand pose estimation from a monocular RGB image. The AGMN consists of two branches of deep convolutional neural networks for calculating unary and pairwise potential functions, followed by a graphical model inference module for integrating unary and pairwise potentials. Unlike existing architectures proposed to combine DCNNs with graphical models, our AGMN is novel in that the parameters of its graphical model are conditioned on and fully adaptive to individual input images. Experiments show that our approach outperforms the state-of-the-art method used in 2D hand keypoints estimation by a notable margin on two public datasets. Code can be found at https://github.com/deyingk/agmn.